• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.290-293
• /
• 2021

In this paper, we implement a learning efficiency verification system to inspire learning motivation and help improve concentration by detecting the situation of the user studying. To this aim, data on learning attitude and concentration are measured by extracting the movement of the user's face or body through a real-time camera. The Jetson board was used to implement the real-time embedded system, and a convolutional neural network (CNN) was implemented for image recognition. After detecting the feature part of the object using a CNN, motion detection is performed. The captured image is shown in a GUI written in PYQT5, and data is collected by sending push messages when each of the actions is obstructed. In addition, each function can be executed on the main screen made with the GUI, and functions such as a statistical graph that calculates the collected data, To do list, and white noise are performed. Through learning efficiency checking system, various functions including data collection and analysis of targets were provided to users.

• Journal of Fashion Business
• /
• v.26 no.2
• /
• pp.129-142
• /
• 2022

The purpose of this study is to develop socks to check the range of ankle movement during squats for men in their late 20s. Sensors of 6, 8, and 12 mm were selected, and each sample was impregnated 1 to 3 times. It was prepared using a CNT dispersion, and the GF value was measured using UTM. Among them, the sample with 2 impregnation showed the best GF value. As a result of applying each sample to the socks, the 12 mm sensor was wider than the area of the Achilles tendon, resulting in noise, and the 8 mm sensor was higher than the tensile strength of the socks, resulting in a decrease in the graph. Therefore, testing was performed using a 6 mm sensor. In order to determine the effectiveness of the sensor, the normal operating range was checked through squats, and significant changes were confirmed when the operating range was checked again through squats by performing operations that can increase the operating range through Gastrocnemius, Soleus stretching, and low lunge. Using the results of this study, it is expected that the average value of the ankle movement range of the user is checked prevent injury, to be provided as basic data for the production of shoe products and the promotion of physical health.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.4 no.6
• /
• pp.164-174
• /
• 1996

This paper presents control and response characteristics of a continuously variable ER(electrorheological) damper for small-sized vehicles. The ER damper is devised and its governing equation of motion is derived from the bond graph model. The field-dependent yield shear stresses are distilled from experimental investigation on the Bingham property of the ER fluid. The distilled data are incorporated into the governing system model and, on the basis of this model, an appropriate size of the ER damper is manufactured. After evaluating the field-dependent damping performance of the proposed ER damper, the skyhook control algorithm is formulated to achieve desired level of the damping force. The controller is then experimentally implemented and control characteristics of the ER damper are presented in order to demonstrate superior controllability of the damping force. In addition, response characteristics of the damping force with respect to the electric field with fast on-off frequency are provided to show the feasibility of practical application.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.522-526
• /
• 2008

모션 캡쳐 장비는 사람의 자연스러운 행동이나 동작 정보를 정밀하게 얻기 위해 널리 사용되며, 영화나 게임과 같은 콘텐츠에서 자주 활용되고 있다. 하지만 모션 캡쳐 장비가 고가이기 때문에 한번 입력받은 데이터를 모션별로 분할하고 상황에 맞게 재결합하여 사용할 필요가 있으며, 입력 데이터를 모션별로 분할하는 것은 대부분 수동으로 이루어진다. 이 때문에 캡쳐된 데이터를 자동으로 분할하기 위한 연구들이 다양하게 시도되고 있다. 기존의 연구들은 크게 전역적 특성에 대한 고려없이 이웃하는 프레임만을 고려하는 온라인 방식과 데이터를 전역적으로 고려하나 이웃하는 프레임 사이의 관계를 고려하지 않는 오프라인 방식으로 나누어진다. 본 논문에서는 온라인과 오프라인 방식을 병합한 그래프 기반의 모션 분할 방법을 제안한다. 분할을 위해 먼저 모션데이터를 기반으로 그래프를 생성하며, 그래프는 이웃하는 각 프레임사이의 유사도뿐만 아니라 시간축을 기반으로 일정시간내의 프레임들의 유사도를 모두 고려하였다. 이렇게 생성된 그래프를 분할하기 위해 분할된 모션내의 유사도 합을 최소화하고 각 모션간의 유사도는 최대화할 수 있는 normalized cuts을 이용하였다. 실험에서 제안된 방법은 기존의 오프라인 방식 중 하나인 GMM과 온라인 방식 중 하나인 국부최소값 분할 방법보다 좋은 결과를 보였으며, 이는 각 프레임 사이의 유사도뿐만 아니라 일정시간내의 유사도를 전역적으로 고려하기 때문이다.

• Proceedings of the KIEE Conference
• /
• 2006.07b
• /
• pp.719-720
• /
• 2006

In the mechanical system, optimization of motion control is very essential in the aspect of automation technique progress. In the servo system, the function of controller is very important but most of the controllers have played only the role of pulse generator because the controller with main function is very expensive. In this thesis, the system was composed of PC, commonly used driver AC servo motor and a produced control board. The PC transmit a gain, a locus data to a driver and controller. At the same time, it converts imformation from the controller and convert them into data and offer an output with graph. The role of a controller is to trasmit a locus data to a driver and counting the pulse on the phase of an encoder to the PC. We have performed the experiment in order to confirm with variable PID parameter capable of the optimization of gain tuning with the counting of feedback control sensor signal with regard to the external interface into the system, such as torque. Based on the experiment result, we have confirmed as follows: First, it was confirmed that we could easily input control factors P.I Gain, constant $K_P,\;K_I$ into PC. Second, not only pulse generator function was possible, but with this pulse it was also possible to count using software with PIC chip. And third, using the multi-purpose PIC micro chip, simple operation and the formation of small size AC Servo Controller was possible.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.15-20
• /
• 2023

Machine learning is comprised of supervised learning, unsupervised learning and reinforcement learning as the type of data and processing mechanism. In this paper, as input and output are unclear and it is difficult to apply the concrete modeling mathematically, reinforcement learning method are applied for crawling robot in this paper. Especially, Q-Learning is the most effective learning technique in model free reinforcement learning. This paper presents a method to implement a crawling robot that is operated by finding the most optimal crawling method through trial and error in a dynamic environment using a Q-learning algorithm. The goal is to perform reinforcement learning to find the optimal two motor angle for the best performance, and finally to maintain the most mature and stable motion about EV3 Crawling robot. In this paper, for the production of the crawling robot, it was produced using Lego Mindstorms with two motors, an ultrasonic sensor, a brick and switches, and EV3 Classroom SW are used for this implementation. By repeating 3 times learning, total 60 data are acquired, and two motor angles vs. crawling distance graph are plotted for the more understanding. Applying the Q-learning reinforcement learning algorithm, it was confirmed that the crawling robot found the optimal motor angle and operated with trained learning, and learn to know the direction for the future research.

• Science of Emotion and Sensibility
• /
• v.25 no.3
• /
• pp.77-90
• /
• 2022

This study seeks to develop a stretch sensor for measuring the wrist movements of people using fishing lures. In order to confirm wrist movement, a stretch sensor was attached to the wrist band, and measurements of the dorsiflexion, plantar flexion, and fishing landing motion were measured using a scale to gauge factor, tensile strength, and elongation recovery rate. A conductive sensor using CNT dispersion was developed and applied to the E-band under the same conditions. A total of 15 sensors of the same size and five types of impregnation once, twice, and three times each were used to measure the gauge factor using UTM. The sensor that was impregnated twice had the best gauge rate, and the prototypes were manufactured with three sensors with high gauge rates and tensile strength. The results of the operation test conducted by connecting to the Arduino showed that Sample 1, which had the highest tensile strength and gauge factor, had a stable graph wavelength in three operations. Samples 2 and 3 showed stable wavelengths in the dorsiflexion and the plantar flexion; however, signal noise appeared in the fishing landing motion. This showed stable wavelengths in the two motions, but the wavelengths of the graphs differ depending on the tensile strength and gauge factor in the fishing landing motion. As a result, it was possible to identify the conditions necessary for manufacturing a stretch sensor for measuring wrist movement. This study will contribute to the development of smart wearable products for lure fishing.

• Journal of KIISE:Software and Applications
• /
• v.32 no.12
• /
• pp.1283-1291
• /
• 2005

One of the problems in boosting Java performance using a Just-in-Time (JIT) compiler is removing redundant array bound checks. In conventional static compilers, many powerful algorithms have been developed, yet they are not directly applicable to JIT compilation where the compilation time is part of the whole running time. In the current JIT compilers, we tan use either a naive algorithm that is not powerful enough or an aggressive algorithm which requires the transformation into a static single assignment (SSA) form of programs (and back to the original form after optimization), thus causing too much overhead not appropriate for JIT compilation This paper proposes a new algorithm based on an inequality graph which can eliminate array bounds check codes aggressively without resorting to the SSA form. When we actually perform this type of optimization, there are many constraints in code motion caused by the precise exception rule in Java specification, which would cause the algorithm to miss many opportunities for eliminating away bound checks. We also propose a new method to overcome these constraints.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.141-148
• /
• 2011

Most of the previous works on scene change detection algorithm focus on the detection of abrupt rather than gradual changes. In general, gradual scene change detection algorithms require heavy computation. Some of those approaches don't consider the error factors such as flashlights, camera or object movements, and special effects. Many scenes change detection algorithms based on the histogram show better performances than other approaches, but they have computation load problem. In this paper, we proposed a scene change detection algorithm with fast and accurate performance using the vertical and horizontal blocked slice images and their macro block informations. We apply graph cut partitioning algorithm for clustering and partitioning of video sequence using generated spatio-temporal histogram. When making spatio-temporal histogram, we only use the central block on vertical and horizontal direction for performance improvement. To detect camera and object movement as well as various special effects accurately, we utilize the motion vector and type information of the macro block.

• Korean Journal of Applied Biomechanics
• /
• v.14 no.3
• /
• pp.17-35
• /
• 2004

The purpose of this study is to explain developmental process of gait via angle-angle diagram to understand how coordinated relationships and control change with age. Twenty four female children, from one to five years of age were the test subjects for this study, and their results were compared to a control group consisting of twenty one adult females. The Vicon 370 CCD camera, VCR, video timer, monitor, and audio visual mixer was utilized to graph the gait cycle for all test subjects. Both coordinated Intra-limb relationships, and range of motion and timing according to quadrant were explained through the angle angle diagram. Movement in the sagittal plane showed both coordinated relationships and control earlier than movement in the coronal or transverse plane. In the sagittal plane, hip and Knee coordinated relationships developed first (from one year of age.) Coordinated relationships in the Knee and ankle and hip and ankle developed next, respectively. Both hip and ankle and knee and ankle development were inhibited by the inability of children to completely perform plantar flexion during the swing and initial double limb support phases. Children appeared to compensate for this by extending at their hip joint more than adults during the third phase, final double limb support. In many cases the angle angle diagram for children had a similar shape as adult's angle angle diagram. This shows that children can coordinate their movements at an early age. However, the magnitudes and timing of children's angle angle diagrams still varied greatly from adults, even at five years of age. This indicates that even at this age, children still do not possess full control of their movements.